© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 58298
    Prev
    Next
    INDEX
    Explanations

    how can asking questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    并ä¸įä¼ļ
    -0.12
    æ°¸è¿ľä¸įä¼ļ
    -0.11
    å¹²åĺĽ
    -0.10
    并ä¸įèĥ½
    -0.10
    大
    -0.10
     ÙħÙĨÙĩ
    -0.09
    {}'.
    -0.09
    _CLI
    -0.09
    飶
    -0.09
    å¯Ĵ
    -0.08
    POSITIVE LOGITS
    ä¸įä¿¡
    0.11
     otherwise
    0.10
    æ²Ļ滩
    0.10
    çľĭå¾ħ
    0.09
    æĴ¼
    0.09
    èĭ«
    0.09
    æī§æĶ¿
    0.09
    åįķ车
    0.09
    ä¸įçIJĨ
    0.08
    ä¸įèĪį
    0.08
    Activations Density 0.016%

    No Known Activations